AI News HubLIVE
原文2 min read

Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

Large Reasoning Models improve by generating intermediate reasoning traces, but this paper reveals that continuing to reason after reaching the correct answer can be harmful. Using a prefix-level trajectory evaluation, they find that stopping at the first correct prefix improves accuracy by up to 21%, while common early stopping methods fail to mitigate harmful overthinking, which is driven by logical drift and visual reinterpretation.

SourcearXiv AIAuthor: Simone Caldarella, Davide Talon, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini

[2606.02835] Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

[Submitted on 1 Jun 2026]

Title:Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models

View a PDF of the paper titled Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models, by Simone Caldarella and 4 other authors

View PDF HTML (experimental)

Abstract:Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assumption that longer reasoning is consistently beneficial remains under-examined. While recent evidence shows that additional reasoning can lead models to overthink, we ask: "Once a model has reached the correct answer, does further reasoning refine the solution, or deviate from it?" To study the dynamics after correctness, we introduce a prefix-level trajectory evaluation protocol grounded in reasoning sufficiency, defining the minimum reasoning budget required for a model to first generate the correct answer. This allows us to disentangle verbose overthinking, where additional reasoning is redundant but harmless, from harmful overthinking, where continued reasoning destabilizes an already-correct trajectory. Starting from multimodal benchmarks, we find that many instances considered reasoning-intensive require surprisingly little reasoning. Moreover, stopping at the first correct prefix improves accuracy over standard reasoning up to 21%, revealing that current models are limited not only by their ability to reason, but also by their inability to stop at the right time. Furthermore, while common efficiency strategies like early stopping substantially reduce verbose overthinking (up to 50%), they fail to mitigate harmful overthinking. Failure analysis reveals that correctness deviations are mainly driven by logical drift and visual reinterpretation. Finally, we show that our findings generalize to language-only reasoning benchmarks, highlighting harmful overthinking as a broader reliability risk. Code available at this https URL.

Subjects:

Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.02835 [cs.AI]

(or arXiv:2606.02835v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.02835

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Simone Caldarella [view email] [v1] Mon, 1 Jun 2026 19:59:27 UTC (1,391 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models, by Simone Caldarella and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)